{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OTD6S6E5FPWBHKAGKSXKXERISR","short_pith_number":"pith:OTD6S6E5","schema_version":"1.0","canonical_sha256":"74c7e9789d2bec13a80654aeab9228946e25be292b6eba41eff380e98d6e3fdc","source":{"kind":"arxiv","id":"2605.18774","version":1},"attestation_state":"computed","paper":{"title":"M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Heuiseok Lim, Jaehyung Seo, Jeongbae Park, Joongmin Shin","submitted_at":"2026-04-17T05:33:45Z","abstract_excerpt":"In long, multi-page industrial documents, retrieval-augmented generation (RAG) depends heavily on whether chunk boundaries follow the document's true structure. Existing text-centric chunkers and generative hierarchy parsers often miss cross-page parent-child relations, figure/table-caption bindings, and boundary cues, which leads to fragmented or redundant chunks and degrades both retrieval and answer quality. We propose M3DocDep, an LVLM-based pipeline that first recovers block-level dependencies and then constructs chunks along the recovered document tree. The pipeline uses SharedDet as a c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.18774","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-04-17T05:33:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"930a0cd9213527181650736615c5634e5d104502c7899decfabc5bd7c31b657c","abstract_canon_sha256":"4d57ac0f4ede39eff63da1733998be86247203646fe5a41f7607665dd6a34859"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:21.385957Z","signature_b64":"Na645/JCQz14ZTW1C3J9pc4iRURTPtv1PzE3NFgZeoyhvLDI5aJM2eyaBwyXQrSy8S/niq9gg1qwflrYUHNCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74c7e9789d2bec13a80654aeab9228946e25be292b6eba41eff380e98d6e3fdc","last_reissued_at":"2026-05-20T00:06:21.385074Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:21.385074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Heuiseok Lim, Jaehyung Seo, Jeongbae Park, Joongmin Shin","submitted_at":"2026-04-17T05:33:45Z","abstract_excerpt":"In long, multi-page industrial documents, retrieval-augmented generation (RAG) depends heavily on whether chunk boundaries follow the document's true structure. Existing text-centric chunkers and generative hierarchy parsers often miss cross-page parent-child relations, figure/table-caption bindings, and boundary cues, which leads to fragmented or redundant chunks and degrades both retrieval and answer quality. We propose M3DocDep, an LVLM-based pipeline that first recovers block-level dependencies and then constructs chunks along the recovered document tree. The pipeline uses SharedDet as a c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18774","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.18774/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.18774","created_at":"2026-05-20T00:06:21.385208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18774v1","created_at":"2026-05-20T00:06:21.385208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18774","created_at":"2026-05-20T00:06:21.385208+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTD6S6E5FPWB","created_at":"2026-05-20T00:06:21.385208+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTD6S6E5FPWBHKAG","created_at":"2026-05-20T00:06:21.385208+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTD6S6E5","created_at":"2026-05-20T00:06:21.385208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTD6S6E5FPWBHKAGKSXKXERISR","json":"https://pith.science/pith/OTD6S6E5FPWBHKAGKSXKXERISR.json","graph_json":"https://pith.science/api/pith-number/OTD6S6E5FPWBHKAGKSXKXERISR/graph.json","events_json":"https://pith.science/api/pith-number/OTD6S6E5FPWBHKAGKSXKXERISR/events.json","paper":"https://pith.science/paper/OTD6S6E5"},"agent_actions":{"view_html":"https://pith.science/pith/OTD6S6E5FPWBHKAGKSXKXERISR","download_json":"https://pith.science/pith/OTD6S6E5FPWBHKAGKSXKXERISR.json","view_paper":"https://pith.science/paper/OTD6S6E5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18774&json=true","fetch_graph":"https://pith.science/api/pith-number/OTD6S6E5FPWBHKAGKSXKXERISR/graph.json","fetch_events":"https://pith.science/api/pith-number/OTD6S6E5FPWBHKAGKSXKXERISR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTD6S6E5FPWBHKAGKSXKXERISR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTD6S6E5FPWBHKAGKSXKXERISR/action/storage_attestation","attest_author":"https://pith.science/pith/OTD6S6E5FPWBHKAGKSXKXERISR/action/author_attestation","sign_citation":"https://pith.science/pith/OTD6S6E5FPWBHKAGKSXKXERISR/action/citation_signature","submit_replication":"https://pith.science/pith/OTD6S6E5FPWBHKAGKSXKXERISR/action/replication_record"}},"created_at":"2026-05-20T00:06:21.385208+00:00","updated_at":"2026-05-20T00:06:21.385208+00:00"}